Claim Missing Document
Check
Articles

EYE DISEASE CLASSIFICATION USING DEEP LEARNING: A COMPARATIVE STUDY OF MOBILENETV2, XCEPTION, AND EFFICIENTNET-B0 Latifa Zahra Agustini; Fitri Bimantoro; Ramaditia Dwiyansaputra
JTIKA (Jurnal Teknik Informatika, Komputer dan Aplikasinya) Vol 8 No 1 (2026): Maret 2026
Publisher : Program Studi Teknik Informatika, Fakultas Teknik, Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jtika.v8i1.518

Abstract

This study presents a comparative analysis of three convolutional neural network (CNN) architectures—MobileNetV2, Xception, and EfficientNet-B0—for classifying retinal fundus images into four categories: Cataract, Diabetic Retinopathy, Glaucoma, and Normal. Using a dataset of 4,217 images, the models were trained with transfer learning, image augmentation, and regularization techniques, and evaluated through 5-fold cross-validation. EfficientNet-B0 achieved the highest mean accuracy (0.85) and demonstrated stable performance across all metrics, while MobileNetV2 provided competitive accuracy with lower computational requirements, making it suitable for resource-limited environments. Xception showed the lowest and least stable performance, indicating a higher tendency to overfit. External validation with clinical images revealed a significant drop in accuracy for all models, highlighting challenges related to domain shift and limited generalization. Grad-CAM analysis also showed difficulties in detecting subtle pathological features in Diabetic Retinopathy and Glaucoma. The study is limited by the small dataset size, reliance on a single data source, and the absence of additional clinical information. Future work should incorporate larger and more diverse datasets, apply domain adaptation strategies, and integrate multimodal clinical data to enhance robustness and clinical applicability.
Matlab Program for Sharpening Image due to Lenses Blurring Effect Simulation with Lucy Richardson Deconvolution Fathony Arroisy Muhammad; Gibran Satya Nugraha; Ramaditia Dwiyansaputra
AMPLITUDO : Journal of Science and Technology Innovation Vol. 2 No. 1 (2023): February
Publisher : Balai Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56566/amplitudo.v2i1.57

Abstract

This research was conducted to simulate digital image sharpening using the Lusi Richardson deconvolution method. Sharpening was then performed by Lusi richardson deconvolution of the pint spread function of the lens effect. This point spread function is modeled mathematically with a mathematical function approach. The results of the convolution between the Digital Image from a photo of an object are then convolved with the point spread function so as to produce a blurry image. The blurry image is then re-sharpened by deconvolution using the Lucy Richardson convolution method. The results of this deconvolution are then compared with the image of an object photo of reference and then the difference is calculated. The slight difference between the deconvolution result image and the original object photo image indicates that the program is running well. Peak Signal to Noise Ratio (PSNR) Is used to determine image sharpening recovery. The optimum sharpening recovery of deconvolution iteration is obtained in the maximum PSNR value
Co-Authors A.M., Mursyidhan Ariefbillah Afwani, Royana Agitha, Nadiyasari Ahmad Zafrullah Ahmad Zafrullah Mardiansyah Ahmad Zafrullah Mardiansyah Akhmad Saufi Amara, Nadya Aranta, Arik Arik Aranta Arik Aranta Arik Aranta Ario Yudo Husodo Ario Yudo Husodo Ario Yudo Husodo Ario Yudo Husodo Ario Yudo Husodo, Ario Yudo Ariyan Zubaidi Ariyan Zubaidi Astrini Widiyanti Azzam Al Husaini Budi Irmawati Budi Irmawati Budiman Rabbani Darmawan, Muhammad Ilham Darmawan, Riski Dewi, Zaskia Elvina Dwi Ratnasari Ekaputra, Galang Prasetya Fadhilah, A. Nur Fathony Arroisy Muhammad Fitri Bimantoro Gibran Satya Nugraha Gibran Satya Nugraha Gibran Satya Nugraha Gibran Satya Nugraha Gibran Satya Nugraha Gibran Satya Nugraha Gibran Satya Nugraha Hadi, Risman Halil Akhyar Hamidi, Mohammad Zaenuddin Hanifah, Fairuz Heri Wijayanto Hidayat, Lalu Ramdoni Hirkan, Muhamad Nurul I Gede Pasek Suta Wijaya I Putu Teguh Putrawan I Wayan Agus Arimbawa Ita Selvia, Siska Ivan Andrianto Jatmika, Andy Hidayat Kasnawi Al Hadi Kokong, Diah Anggreni Ratna Sari Kusuma, Fendi Putra Latifa Zahra Agustini Made Agus Dwiputra Manuaba, Ida Bagus Ryand Wirayana Maulana, Sutan Fajri Maz Isa Ansyori Mindi Richia Putri Mochammad Dinta Alif Syaifuddin Mohammad Zaenuddin Hamidi Muhamad Singgih Muhammad Azmi Muhammad Daden Kasandi Putra Wesa Muhammad Dani Muhammad Giri Restu Adjie Muhammad Husnul Ramdani Muhammad Muaidi Muhammad Mukaddam Alaydrus Muhlis Fathurrahman Muvianto, Cahyo Mustiko Okta Ni Ketut Anggriani Noor Alamsyah Nugraha, Gibran Satya Nurfauziyah Nurfauziyah Nurhasiyah Nurhasiyah Nurun Latifah Pahrul Irfan Pahrul Irfan Paramarta, Muhammad Magistra Apta Rahayu, Sefani Cahyo Auliya Raphael Bianco Huwae Rassy, Regania Pasca Rizqullah, Muhammad Naufal Robby Igfirly Mustaib Rohmawati, S. Antya Royana Afwani Salsabila, Raissa Calista Santi Ika Murpratiwi Selvira Anandia Intan Maulidya Siska Ita Selvia Suhada, Destia Susi Rahayu Susi Rahayu Sutiyasning Tiara, Baiq Najwa Tresna, I Made Agus Wahyuni Sulastri Wahyuningsih Wahyuningsih Widiarta, I Putu Angga Purnama Widiyanti, Astrini Wirarama Wedashwara Wirararama Wedashwara